Icing is an important factor threatening aircraft flight safety.According to the requirements of airworthiness regulations,aircraft icing safety assessment is needed to be carried out based on the ice shapes formed un...Icing is an important factor threatening aircraft flight safety.According to the requirements of airworthiness regulations,aircraft icing safety assessment is needed to be carried out based on the ice shapes formed under different icing conditions.Due to the complexity of the icing process,the rapid assessment of ice shape remains an important challenge.In this paper,an efficient prediction model of aircraft icing is established based on the deep belief network(DBN)and the stacked auto-encoder(SAE),which are all deep neural networks.The detailed network structures are designed and then the networks are trained according to the samples obtained by the icing numerical computation.After that the model is applied on the ice shape evaluation of NACA0012 airfoil.The results show that the model can accurately capture the nonlinear behavior of aircraft icing and thus make an excellent ice shape prediction.The model provides an important tool for aircraft icing analysis.展开更多
To improve magnetotelluric(MT)nonlinear inversion accuracy and stability,this work introduces the deep belief network(DBN)algorithm.Firstly,a network frame is set up for training in different 2D MT models.The network ...To improve magnetotelluric(MT)nonlinear inversion accuracy and stability,this work introduces the deep belief network(DBN)algorithm.Firstly,a network frame is set up for training in different 2D MT models.The network inputs are the apparent resistivities of known models,and the outputs are the model parameters.The optimal network structure is achieved by determining the numbers of hidden layers and network nodes.Secondly,the learning process of the DBN is implemented to obtain the optimal solution of network connection weights for known geoelectric models.Finally,the trained DBN is verified through inversion tests,in which the network inputs are the apparent resistivities of unknown models,and the outputs are the corresponding model parameters.The experiment results show that the DBN can make full use of the global searching capability of the restricted Boltzmann machine(RBM)unsupervised learning and the local optimization of the back propagation(BP)neural network supervised learning.Comparing to the traditional neural network inversion,the calculation accuracy and stability of the DBN for MT data inversion are improved significantly.And the tests on synthetic data reveal that this method can be applied to MT data inversion and achieve good results compared with the least-square regularization inversion.展开更多
Precise fault diagnosis is an important part of prognostics and health management. It can avoid accidents, extend the service life of the machine, and also reduce maintenance costs. For gas turbine engine fault diagno...Precise fault diagnosis is an important part of prognostics and health management. It can avoid accidents, extend the service life of the machine, and also reduce maintenance costs. For gas turbine engine fault diagnosis, we cannot install too many sensors in the engine because the operating environment of the engine is harsh and the sensors will not work in high temperature, at high rotation speed, or under high pressure. Thus, there is not enough sensory data from the working engine to diagnose potential failures using existing approaches. In this paper, we consider the problem of engine fault diagnosis using finite sensory data under complicated circumstances, and propose deep belief networks based on information entropy, IE-DBNs, for engine fault diagnosis. We first introduce several information entropies and propose joint complexity entropy based on single signal entropy. Second, the deep belief networks （DBNs） is analyzed and a logistic regression layer is added to the output of the DBNs. Then, information entropy is used in fault diagnosis and as the input for the DBNs. Comparison between the proposed IE-DBNs method and state-of-the-art machine learning approaches shows that the IE-DBNs method achieves higher accuracy.展开更多
Unconstrained offiine handwriting recognition is a challenging task in the areas of document analysis and pattern recognition. In recent years, to sufficiently exploit the supervisory information hidden in document im...Unconstrained offiine handwriting recognition is a challenging task in the areas of document analysis and pattern recognition. In recent years, to sufficiently exploit the supervisory information hidden in document images, much effort has been made to integrate multi-layer perceptrons （MLPs） in either a hybrid or a tandem fashion into hidden Markov models （HMMs）. However, due to the weak learnability of MLPs, the learnt features are not necessarily optimal for subsequent recognition tasks. In this paper, we propose a deep architecture-based tandem approach for unconstrained offiine handwriting recognition. In the proposed model, deep belief networks arc adopted to learn the compact representations of sequential data, while HMMs are applied for （sub-）word recognition. We evaluate the proposed model on two publicly available datasets, i.e., RIMES and IFN/ENIT, which are based on Latin and Arabic languages respectively, and one dataset collected by ourselves called Devanagari （all Indian script）. Extensive experiments show the advantage of the proposed model, especially over the MLP-HMMs taudem approaches.展开更多
基金supported in part by the National Natural Science Foundation of China(No.51606213)the National Major Science and Technology Projects(No.J2019-III-0010-0054)。
文摘Icing is an important factor threatening aircraft flight safety.According to the requirements of airworthiness regulations,aircraft icing safety assessment is needed to be carried out based on the ice shapes formed under different icing conditions.Due to the complexity of the icing process,the rapid assessment of ice shape remains an important challenge.In this paper,an efficient prediction model of aircraft icing is established based on the deep belief network(DBN)and the stacked auto-encoder(SAE),which are all deep neural networks.The detailed network structures are designed and then the networks are trained according to the samples obtained by the icing numerical computation.After that the model is applied on the ice shape evaluation of NACA0012 airfoil.The results show that the model can accurately capture the nonlinear behavior of aircraft icing and thus make an excellent ice shape prediction.The model provides an important tool for aircraft icing analysis.
基金Project(41304090)supported by the National Natural Science Foundation of ChinaProject(2016YFC0303104)supported by the National Key Research and Development Project of ChinaProject(DY135-S1-1-07)supported by Ocean 13th Five-Year International Marine Resources Survey and Development of China
文摘To improve magnetotelluric(MT)nonlinear inversion accuracy and stability,this work introduces the deep belief network(DBN)algorithm.Firstly,a network frame is set up for training in different 2D MT models.The network inputs are the apparent resistivities of known models,and the outputs are the model parameters.The optimal network structure is achieved by determining the numbers of hidden layers and network nodes.Secondly,the learning process of the DBN is implemented to obtain the optimal solution of network connection weights for known geoelectric models.Finally,the trained DBN is verified through inversion tests,in which the network inputs are the apparent resistivities of unknown models,and the outputs are the corresponding model parameters.The experiment results show that the DBN can make full use of the global searching capability of the restricted Boltzmann machine(RBM)unsupervised learning and the local optimization of the back propagation(BP)neural network supervised learning.Comparing to the traditional neural network inversion,the calculation accuracy and stability of the DBN for MT data inversion are improved significantly.And the tests on synthetic data reveal that this method can be applied to MT data inversion and achieve good results compared with the least-square regularization inversion.
文摘Precise fault diagnosis is an important part of prognostics and health management. It can avoid accidents, extend the service life of the machine, and also reduce maintenance costs. For gas turbine engine fault diagnosis, we cannot install too many sensors in the engine because the operating environment of the engine is harsh and the sensors will not work in high temperature, at high rotation speed, or under high pressure. Thus, there is not enough sensory data from the working engine to diagnose potential failures using existing approaches. In this paper, we consider the problem of engine fault diagnosis using finite sensory data under complicated circumstances, and propose deep belief networks based on information entropy, IE-DBNs, for engine fault diagnosis. We first introduce several information entropies and propose joint complexity entropy based on single signal entropy. Second, the deep belief networks （DBNs） is analyzed and a logistic regression layer is added to the output of the DBNs. Then, information entropy is used in fault diagnosis and as the input for the DBNs. Comparison between the proposed IE-DBNs method and state-of-the-art machine learning approaches shows that the IE-DBNs method achieves higher accuracy.
基金the National Natural Science Foundation of China （No. 61403353）
文摘Unconstrained offiine handwriting recognition is a challenging task in the areas of document analysis and pattern recognition. In recent years, to sufficiently exploit the supervisory information hidden in document images, much effort has been made to integrate multi-layer perceptrons （MLPs） in either a hybrid or a tandem fashion into hidden Markov models （HMMs）. However, due to the weak learnability of MLPs, the learnt features are not necessarily optimal for subsequent recognition tasks. In this paper, we propose a deep architecture-based tandem approach for unconstrained offiine handwriting recognition. In the proposed model, deep belief networks arc adopted to learn the compact representations of sequential data, while HMMs are applied for （sub-）word recognition. We evaluate the proposed model on two publicly available datasets, i.e., RIMES and IFN/ENIT, which are based on Latin and Arabic languages respectively, and one dataset collected by ourselves called Devanagari （all Indian script）. Extensive experiments show the advantage of the proposed model, especially over the MLP-HMMs taudem approaches.
